© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25137
    Prev
    Next
    INDEX
    Explanations

    locations with dates

    np_acts-logits-general · gemini-2.5-flash-lite

    units of length and energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    인
    0.48
    ید
    0.48
     Scientist
    0.46
     Adriatic
    0.44
     United
    0.44
     International
    0.44
    ד
    0.44
     CERN
    0.43
     World
    0.43
     positrons
    0.42
    POSITIVE LOGITS
     आम्ही
    0.47
    痔
    0.47
    expressed
    0.46
     ಮಾತ
    0.45
    ವೂ
    0.45
     돌아
    0.44
    thebetter
    0.44
    arnings
    0.44
    cents
    0.44
    ftar
    0.42
    Activations Density 0.000%

    No Known Activations